Intelligent Autonomic Computing: Achieving Self-Optimization Through Autonomous Learning
R Radha, Rathnakar Achary, P. Mano Paul · 2025
This work presents an intelligent autonomic computing framework that is supposed to strengthen selfoptimization by means of autonomous learning. The purpose is to endow mechanical systems with the capability of adaptively responding by automating resources, tuning their operation, and adapting to environmental conditions with little human intervention. Through the borrowing of control theory, predictive analytics, and machine learning, the model provides timely informed decision-making that is in real-time. The framework presents a dynamic resource allocation scheme which is compared against performance indicators such as Resource Efficiency, Training Cycle Length, and Predictive Accuracy. Enhanced performance in terms of system efficiency and responsiveness was noted proclaiming the possibility of advantages towards industrial automation smart factories and cyber-physical systems.